Next move in movement disorders (NEMO): developing a computer-aided classification tool for hyperkinetic movement...

Area of Science:

• Neurology
• Biomedical Engineering
• Data Science

Background:

• Hyperkinetic movement disorders require accurate classification for effective diagnosis and treatment.
• Current classification methods can be time-consuming and subjective.
• A novel, objective approach is needed to improve diagnostic accuracy and speed.

Purpose of the Study:

• To develop a computer-aided classification tool for hyperkinetic movement disorders.
• To integrate clinical information, electromyography (EMG), accelerometry, and video data.
• To advance rapid and accurate phenotype classification for improved patient care.

Main Methods:

• The Next Move in Movement Disorders (NEMO) study is a cross-sectional study.
• Patients with single and mixed phenotype movement disorders are included.
• Machine learning algorithms, including deep learning, will analyze EMG, accelerometry, and 3D video data from specific movement tasks.
• Expert-based classification provides labels for supervised learning.

Main Results:

• The study will compare manually engineered features with deep learning methods for classification.
• Visual analytics will be used to understand the algorithm's decision-making process.
• The developed tool is expected to provide accurate and rapid classification of movement disorder phenotypes.

Conclusions:

• This research pioneers the application of machine learning in movement disorder classification.
• The computer-aided tool has the potential to significantly improve the diagnostic process.
• Findings will be disseminated through publications and patient communications.